CN112200136A - Certificate authenticity identification method and device, computer readable medium and electronic equipment - Google Patents
Certificate authenticity identification method and device, computer readable medium and electronic equipment Download PDFInfo
- Publication number
- CN112200136A CN112200136A CN202011179992.0A CN202011179992A CN112200136A CN 112200136 A CN112200136 A CN 112200136A CN 202011179992 A CN202011179992 A CN 202011179992A CN 112200136 A CN112200136 A CN 112200136A
- Authority
- CN
- China
- Prior art keywords
- counterfeiting
- authenticity
- certificate
- point
- video image
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 63
- 230000003068 static effect Effects 0.000 claims abstract description 156
- 230000008859 change Effects 0.000 claims abstract description 30
- 238000012545 processing Methods 0.000 claims description 50
- 238000001514 detection method Methods 0.000 claims description 48
- 238000010586 diagram Methods 0.000 claims description 25
- 238000004590 computer program Methods 0.000 claims description 14
- 230000007306 turnover Effects 0.000 claims description 11
- 238000005070 sampling Methods 0.000 claims description 10
- 238000000605 extraction Methods 0.000 claims description 9
- 239000000284 extract Substances 0.000 claims description 7
- 230000006870 function Effects 0.000 description 12
- 230000008569 process Effects 0.000 description 11
- 238000004891 communication Methods 0.000 description 7
- 238000012795 verification Methods 0.000 description 6
- 230000009471 action Effects 0.000 description 5
- 238000005286 illumination Methods 0.000 description 5
- 230000003287 optical effect Effects 0.000 description 4
- 238000004364 calculation method Methods 0.000 description 3
- 238000012549 training Methods 0.000 description 3
- 238000013528 artificial neural network Methods 0.000 description 2
- 238000004422 calculation algorithm Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000007639 printing Methods 0.000 description 2
- 230000000644 propagated effect Effects 0.000 description 2
- 230000011218 segmentation Effects 0.000 description 2
- 239000004065 semiconductor Substances 0.000 description 2
- 238000012706 support-vector machine Methods 0.000 description 2
- 238000012935 Averaging Methods 0.000 description 1
- 235000018893 Cercis canadensis var canadensis Nutrition 0.000 description 1
- 240000000024 Cercis siliquastrum Species 0.000 description 1
- 230000006978 adaptation Effects 0.000 description 1
- 230000001413 cellular effect Effects 0.000 description 1
- 238000013527 convolutional neural network Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 238000003709 image segmentation Methods 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 238000010295 mobile communication Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 230000036544 posture Effects 0.000 description 1
- 208000011580 syndromic disease Diseases 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/82—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using neural networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/40—Scenes; Scene-specific elements in video content
- G06V20/46—Extracting features or characteristics from the video content, e.g. video fingerprints, representative shots or key frames
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2411—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on the proximity to a decision surface, e.g. support vector machines
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T3/00—Geometric image transformations in the plane of the image
- G06T3/40—Scaling of whole images or parts thereof, e.g. expanding or contracting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/70—Determining position or orientation of objects or cameras
- G06T7/73—Determining position or orientation of objects or cameras using feature-based methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/25—Determination of region of interest [ROI] or a volume of interest [VOI]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/77—Processing image or video features in feature spaces; using data integration or data reduction, e.g. principal component analysis [PCA] or independent component analysis [ICA] or self-organising maps [SOM]; Blind source separation
- G06V10/7715—Feature extraction, e.g. by transforming the feature space, e.g. multi-dimensional scaling [MDS]; Mappings, e.g. subspace methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/40—Scenes; Scene-specific elements in video content
- G06V20/49—Segmenting video sequences, i.e. computational techniques such as parsing or cutting the sequence, low-level clustering or determining units such as shots or scenes
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/95—Pattern authentication; Markers therefor; Forgery detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V30/00—Character recognition; Recognising digital ink; Document-oriented image-based pattern recognition
- G06V30/40—Document-oriented image-based pattern recognition
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V30/00—Character recognition; Recognising digital ink; Document-oriented image-based pattern recognition
- G06V30/40—Document-oriented image-based pattern recognition
- G06V30/41—Analysis of document content
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/0464—Convolutional networks [CNN, ConvNet]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/09—Supervised learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10016—Video; Image sequence
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20084—Artificial neural networks [ANN]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30176—Document
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Multimedia (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- Computing Systems (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Software Systems (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Medical Informatics (AREA)
- General Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Biophysics (AREA)
- Mathematical Physics (AREA)
- Molecular Biology (AREA)
- Computational Linguistics (AREA)
- Biomedical Technology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Biology (AREA)
- Image Analysis (AREA)
- Image Processing (AREA)
Abstract
The embodiment of the application provides a certificate authenticity identification method and device, a computer readable medium and electronic equipment. The certificate authenticity identification method comprises the following steps: detecting dynamic anti-counterfeiting points and static anti-counterfeiting points contained in a plurality of certificate images of a target certificate, wherein the plurality of certificate images are obtained by carrying out image acquisition on the target certificate at different angles; extracting image characteristic information of the position of the static anti-counterfeiting point to obtain the characteristic of the static anti-counterfeiting point, and extracting image characteristic information of the position of the dynamic anti-counterfeiting point and change characteristic information of the dynamic anti-counterfeiting point among a plurality of certificate images to obtain the characteristic of the dynamic anti-counterfeiting point; identifying the authenticity result corresponding to each static anti-counterfeiting point based on the characteristics of the static anti-counterfeiting points, and identifying the authenticity result corresponding to each dynamic anti-counterfeiting point based on the characteristics of the dynamic anti-counterfeiting points; and determining the authenticity of the target certificate according to the authenticity result corresponding to each static anti-counterfeiting point and the authenticity result corresponding to each dynamic anti-counterfeiting point. The technical scheme of the application can accurately identify the authenticity of the certificate.
Description
Technical Field
The application relates to the technical field of computers and communication, in particular to a certificate authenticity identification method and device, a computer readable medium and electronic equipment.
Background
In daily life, people often need to upload a document image (such as an identity card, a driving license and the like) on the internet to perform identity verification based on the document image. However, in the authentication, there may be a counterfeit document image that is maliciously forged and uploaded by the user, and thus, it is necessary to identify the authenticity of the document. However, the certificate authenticity identification method proposed in the related technology has the problems of low identification accuracy and the like.
Disclosure of Invention
Embodiments of the present application provide a method and an apparatus for identifying authenticity of a certificate, a computer readable medium, and an electronic device, so that authenticity of a certificate can be accurately identified at least to a certain extent.
Other features and advantages of the present application will be apparent from the following detailed description, or may be learned by practice of the application.
According to an aspect of an embodiment of the present application, there is provided a certificate authenticity identification method, including: detecting dynamic anti-counterfeiting points and static anti-counterfeiting points contained in a plurality of certificate images of a target certificate, wherein the plurality of certificate images are obtained by carrying out image acquisition on the target certificate at different angles; extracting image characteristic information of the position of the static anti-counterfeiting point to obtain the characteristic of the static anti-counterfeiting point, and extracting image characteristic information of the position of the dynamic anti-counterfeiting point and change characteristic information of the dynamic anti-counterfeiting point among a plurality of certificate images to obtain the characteristic of the dynamic anti-counterfeiting point; identifying the authenticity result corresponding to each static anti-counterfeiting point based on the static anti-counterfeiting point characteristics, and identifying the authenticity result corresponding to each dynamic anti-counterfeiting point based on the dynamic anti-counterfeiting point characteristics; and determining the authenticity of the target certificate according to the authenticity result corresponding to each static anti-counterfeiting point and the authenticity result corresponding to each dynamic anti-counterfeiting point.
According to an aspect of an embodiment of the present application, there is provided a certificate authenticity identifying apparatus including: the system comprises an anti-counterfeiting point detection unit, a verification unit and a verification unit, wherein the anti-counterfeiting point detection unit is configured to detect dynamic anti-counterfeiting points and static anti-counterfeiting points contained in a plurality of certificate images of a target certificate, and the plurality of certificate images are obtained by carrying out image acquisition on the target certificate through different angles; the extraction unit is configured to extract image characteristic information of the position of the static anti-counterfeiting point to obtain a static anti-counterfeiting point characteristic, and extract image characteristic information of the position of the dynamic anti-counterfeiting point and change characteristic information of the dynamic anti-counterfeiting point among a plurality of certificate images to obtain a dynamic anti-counterfeiting point characteristic; the processing unit is configured to identify the authenticity result corresponding to each static anti-counterfeiting point based on the static anti-counterfeiting point characteristics and identify the authenticity result corresponding to each dynamic anti-counterfeiting point based on the dynamic anti-counterfeiting point characteristics; and the determining unit is configured to determine the authenticity of the target certificate according to the authenticity results corresponding to the static anti-counterfeiting points and the authenticity results corresponding to the dynamic anti-counterfeiting points.
In some embodiments of the present application, based on the foregoing solution, the certificate authenticity identifying apparatus further includes: the device comprises an acquisition unit, a position detection unit and an acquisition unit; wherein the capture unit is configured to capture video streams containing the target document from different angles; the position detection unit is configured to detect the position of a target certificate contained in a video image frame in the video stream; the acquisition unit is further configured to: if the position detection unit detects that the position of the target certificate does not accord with the set condition, the video stream containing the target certificate is collected again until the position of the target certificate contained in the collected video image frame accords with the set condition; the acquisition unit is configured to: and if the position of the target certificate is detected to accord with the set condition, acquiring the plurality of certificate images from the video image frames contained in the video stream.
In some embodiments of the present application, based on the foregoing solution, the position detection unit is configured to: performing downsampling processing on the video image frame through a plurality of sequentially connected convolution blocks, wherein a first convolution block in the plurality of convolution blocks is used for performing downsampling processing on the video image frame, an i +1 th convolution block in the plurality of convolution blocks is used for performing downsampling processing on an output feature map of the i-th convolution block, and i is larger than 0; sequentially carrying out upsampling processing on the corresponding feature map of the (i + 1) th volume block in the plurality of volume blocks, merging the result of the upsampling processing with the output feature map of the ith volume block, and taking the merged result as the corresponding feature map of the ith volume block, wherein the upsampling processing and the downsampling processing have the same sampling scale; and identifying the position of a target certificate contained in the video image frame according to the corresponding characteristic map of the first volume block in the plurality of volume blocks.
In some embodiments of the present application, based on the foregoing solution, the certificate authenticity identifying apparatus further includes: the angle detection unit is configured to detect the turning angle of a target certificate contained in a video image frame in the video stream; the acquisition unit is further configured to: if the detected turnover angle of the target certificate does not accord with the set condition, the video stream containing the target certificate is collected again until the turnover angle of the target certificate contained in the collected video image frame accords with the set condition.
In some embodiments of the present application, based on the foregoing solution, the angle detection unit is configured to: performing target certificate detection in video image frames contained in the video stream to identify a certificate detection frame containing the target certificate in the video image frames; and determining the turning angle of the target certificate contained in the video image frame according to the side length ratio of the certificate detection frame identified in the video image frame.
In some embodiments of the present application, based on the foregoing scheme, the extracting unit extracts image feature information of a position where the dynamic anti-counterfeit point is located and change feature information of the dynamic anti-counterfeit point between a plurality of certificate images to obtain a process of a dynamic anti-counterfeit point feature, and the processing unit identifies a process of a true and false result corresponding to each dynamic anti-counterfeit point based on the dynamic anti-counterfeit point feature, including: inputting a plurality of certificate image frames containing the dynamic anti-counterfeiting points into a three-dimensional convolution network so as to extract a multi-dimensional feature map of the dynamic anti-counterfeiting points through the three-dimensional convolution network; and converting the multidimensional characteristic diagram into a one-dimensional characteristic diagram through a down-sampling unit in the three-dimensional convolution network, and outputting an authenticity result corresponding to the dynamic anti-counterfeiting point through a full-connection layer in the three-dimensional convolution network.
In some embodiments of the present application, based on the foregoing solution, the processing unit is configured to: determining the authenticity result corresponding to each static anti-counterfeiting point according to a first characteristic value interval in which the static anti-counterfeiting point characteristic of each static anti-counterfeiting point is located and the authenticity result associated with the first characteristic value interval; and determining the authenticity result corresponding to each dynamic anti-counterfeiting point according to a second characteristic value interval where the dynamic anti-counterfeiting point of each dynamic anti-counterfeiting point is positioned and the authenticity result associated with the second characteristic value interval.
In some embodiments of the present application, based on the foregoing solution, the plurality of document images includes: a designated video image frame extracted from a video stream containing the target credential, the designated video image frame comprising any of: each video image frame in the video stream, one or more video image frames extracted from the video stream according to a set interval, and the video image frame of which the target certificate is in a horizontal position; the extraction unit is configured to: and extracting image characteristic information of the position of the static anti-counterfeiting point in the appointed video image frame.
In some embodiments of the present application, based on the foregoing solution, the processing unit is configured to: identifying the authenticity result of the static anti-counterfeiting points contained in each appointed video image frame based on the static anti-counterfeiting point characteristics extracted from each appointed video image frame; determining the authenticity results of the same static anti-counterfeiting point in each appointed video image frame according to the authenticity results of the static anti-counterfeiting points contained in each appointed video image frame; and calculating the authenticity result of each static anti-counterfeiting point on the target certificate according to the authenticity result of the same static anti-counterfeiting point in each appointed video image frame.
In some embodiments of the present application, based on the foregoing solution, the plurality of document images includes: at least one set of video image frames extracted from a video stream containing the target document; the extraction unit is configured to: and extracting image characteristic information of the position of the dynamic anti-counterfeiting point and the change characteristic information of the dynamic anti-counterfeiting point from the at least one group of video image frames.
In some embodiments of the present application, based on the foregoing solution, the processing unit is configured to: if a plurality of groups of video image frames are extracted from the video stream containing the target certificate, identifying the authenticity results of the dynamic anti-counterfeiting points contained in each group of video image frames based on the image characteristic information of the positions of the dynamic anti-counterfeiting points extracted from each group of video image frames and the change characteristic information of the dynamic anti-counterfeiting points; determining the authenticity results of the same dynamic anti-counterfeiting point in each group of video image frames according to the authenticity results of the dynamic anti-counterfeiting points contained in each group of video image frames; and calculating the authenticity result of each dynamic anti-counterfeiting point on the target certificate according to the authenticity result of the same dynamic anti-counterfeiting point in each group of video image frames.
In some embodiments of the present application, based on the foregoing scheme, the authenticity result includes an authenticity confidence; the determination unit is configured to: weighting the authenticity confidence corresponding to each static anti-counterfeiting point and the authenticity confidence corresponding to each dynamic anti-counterfeiting point according to the weight of each static anti-counterfeiting point and the weight of each dynamic anti-counterfeiting point to obtain a true and false confidence comprehensive value; and determining the authenticity of the target certificate according to the authenticity confidence coefficient comprehensive value.
According to an aspect of embodiments of the present application, there is provided a computer-readable medium having stored thereon a computer program which, when executed by a processor, implements a method of identifying authenticity of a document as described in the above embodiments.
According to an aspect of an embodiment of the present application, there is provided an electronic device including: one or more processors; a storage device for storing one or more programs which, when executed by the one or more processors, cause the one or more processors to implement the method of certificate authenticity identification as described in the above embodiments.
According to an aspect of embodiments herein, there is provided a computer program product or computer program comprising computer instructions stored in a computer readable storage medium. The processor of the computer device reads the computer instructions from the computer readable storage medium, and executes the computer instructions, so that the computer device executes the certificate authenticity identification method provided in the various optional embodiments.
In some embodiments of the present application, by detecting the dynamic anti-counterfeit dots and the static anti-counterfeit dots included in the multiple document images of the target document, the image feature information of the positions of the static anti-counterfeit dots can be extracted to obtain the static anti-counterfeit dot features, the image feature information of the positions of the dynamic anti-counterfeit dots and the variation feature information of the dynamic anti-counterfeit dots among the multiple document images are extracted to obtain the dynamic anti-counterfeit dot features, and the corresponding authenticity results of the static anti-counterfeit dots are identified based on the static anti-counterfeit dot features, the corresponding authenticity results of the dynamic anti-counterfeit dots are identified based on the dynamic anti-counterfeit dot features, and the authenticity of the target document is determined according to the corresponding authenticity results of the static anti-counterfeit dots and the corresponding authenticity results of the dynamic anti-counterfeit dots. It can be seen that the technical scheme of this application embodiment can carry out the discernment of certificate true and false based on dynamic anti-fake point and static anti-fake point on the certificate image jointly, to dynamic anti-fake point, not only considered the image characteristic information of dynamic anti-fake point position, considered the change characteristic information of dynamic anti-fake point between a plurality of certificate images moreover, and then make the true and false of target certificate of true and false result that corresponds according to the true and false result that each static anti-fake point corresponds and the true and false result that each dynamic anti-fake point corresponds come the discernment, improved the accuracy of certificate true and false discernment.
It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the application.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and together with the description, serve to explain the principles of the application. It is obvious that the drawings in the following description are only some embodiments of the application, and that for a person skilled in the art, other drawings can be derived from them without inventive effort. In the drawings:
FIG. 1 shows a schematic diagram of an exemplary system architecture to which aspects of embodiments of the present application may be applied;
FIG. 2 shows a flow diagram of a method of document authenticity identification according to an embodiment of the application;
FIG. 3 illustrates a schematic view of a scene where multiple document images are acquired by image capturing a target document from different angles according to one embodiment of the present application;
FIG. 4 illustrates a schematic view of a scene where multiple document images are acquired by image capturing a target document from different angles according to one embodiment of the present application;
FIG. 5 illustrates a flow diagram for detecting a location of a target document based on image segmentation according to one embodiment of the present application;
FIG. 6 is a schematic diagram illustrating an authenticity result corresponding to a dynamic anti-counterfeit point for identification by a three-dimensional convolution network according to an embodiment of the present application;
FIG. 7 shows a flow diagram of a method of document authenticity identification according to an embodiment of the application;
FIG. 8 shows a block diagram of a certificate authenticity identification device according to one embodiment of the present application;
FIG. 9 illustrates a schematic structural diagram of a computer system suitable for use in implementing the electronic device of an embodiment of the present application.
Detailed Description
Example embodiments will now be described more fully with reference to the accompanying drawings. Example embodiments may, however, be embodied in many different forms and should not be construed as limited to the examples set forth herein; rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the concept of example embodiments to those skilled in the art.
Furthermore, the described features, structures, or characteristics may be combined in any suitable manner in one or more embodiments. In the following description, numerous specific details are provided to give a thorough understanding of embodiments of the application. One skilled in the relevant art will recognize, however, that the subject matter of the present application can be practiced without one or more of the specific details, or with other methods, components, devices, steps, and so forth. In other instances, well-known methods, devices, implementations, or operations have not been shown or described in detail to avoid obscuring aspects of the application.
The block diagrams shown in the figures are functional entities only and do not necessarily correspond to physically separate entities. I.e. these functional entities may be implemented in the form of software, or in one or more hardware modules or integrated circuits, or in different networks and/or processor means and/or microcontroller means.
The flow charts shown in the drawings are merely illustrative and do not necessarily include all of the contents and operations/steps, nor do they necessarily have to be performed in the order described. For example, some operations/steps may be decomposed, and some operations/steps may be combined or partially combined, so that the actual execution sequence may be changed according to the actual situation.
It should be noted that: reference herein to "a plurality" means two or more. "and/or" describe the association relationship of the associated objects, meaning that there may be three relationships, e.g., A and/or B may mean: a exists alone, A and B exist simultaneously, and B exists alone. The character "/" generally indicates that the former and latter associated objects are in an "or" relationship.
Credentials refer to certificates and documents used to prove identity, experience, and the like. There are many types of documents, such as IC contactless smart documents, which have a built-in chip that provides a certain storage space for storing the photos of the credential person in addition to the basic information of the credential person, such as name, sex, date of birth, address, etc. Regardless of the type of document, a security mark is typically provided to facilitate verification of the authenticity of the document.
In order to verify the authenticity of a document, it is common to compare the information read from a chip (e.g., an IC contactless smart document) with the information derived from an identity information base, or to compare the similarity between a face photograph read from the chip and a photograph printed on the surface of the document to determine the authenticity of the document.
However, the scheme for verifying authenticity needs to rely on a special chip reading tool to read information, and the verification process also needs to be compared manually one by one, the reliability of the whole verification process is closely related to the experience and subjective identification capability of workers, the subjective identification capability of each person is different, the emphasis points are also different, the comparison process is not only lack of scientific basis, but also lack of uniform standard, and is easily influenced by various factors.
Based on this, the embodiment of the application provides a new certificate authenticity identification method, which can identify the authenticity of a certificate based on a dynamic anti-counterfeiting point and a static anti-counterfeiting point on a certificate image, for the static anti-counterfeiting point, the image characteristic information of the position of the static anti-counterfeiting point is considered, for the dynamic anti-counterfeiting point, the image characteristic information of the position of the dynamic anti-counterfeiting point is considered, the change characteristic information of the dynamic anti-counterfeiting point among a plurality of certificate images is considered, the authenticity result corresponding to each static anti-counterfeiting point and the authenticity result corresponding to each dynamic anti-counterfeiting point can be determined first, the authenticity of a target is identified according to the authenticity result corresponding to each static anti-counterfeiting point and the authenticity result corresponding to each dynamic anti-counterfeiting point, and the authenticity identification accuracy of the authenticity of the certificate is improved.
Specifically, in one system architecture of the present application, as shown in fig. 1, the system architecture 100 may include a terminal 101 (the terminal 101 may be a smartphone as shown in fig. 1, or may also be a tablet, a portable computer, a desktop computer, etc.), a network 102 and a server 103. Network 102 serves as a medium for providing communication links between terminals 101 and servers 103. Network 102 may include, but is not limited to: a wireless network, a wired network, including but not limited to at least one of: wide area networks, metropolitan area networks, and local area networks. The wireless network includes, but is not limited to, at least one of: bluetooth, WI-FI, Near Field Communication (NFC for short), cellular mobile Communication networks, etc. A user may use the terminal 101 to interact with the server 103 via the network 102 to receive or send messages or the like.
It should be understood that the number of terminals 101, networks 102 and servers 103 in fig. 1 is merely illustrative. There may be any number of terminals 101, networks 102, and servers 103, as desired for implementation. For example, the server 103 may be a server cluster composed of a plurality of servers.
In one embodiment of the present application, the terminal 101 may capture images of the target certificate 104 to be authenticated at different angles, and then send a plurality of certificate images captured at different angles to the server 103 via the network 102. After receiving the plurality of certificate images, the server 103 detects the static anti-counterfeiting points and the dynamic anti-counterfeiting points included in each certificate image, extracts image characteristic information of the positions of the static anti-counterfeiting points to obtain static anti-counterfeiting point characteristics, and extracts image characteristic information of the positions of the dynamic anti-counterfeiting points and change characteristic information of the dynamic anti-counterfeiting points among the plurality of certificate images to obtain dynamic anti-counterfeiting point characteristics. After the static anti-counterfeiting point characteristics and the static anti-counterfeiting point characteristics are obtained, the authenticity results corresponding to the static anti-counterfeiting points can be identified based on the static anti-counterfeiting point characteristics, the authenticity results corresponding to the dynamic anti-counterfeiting points are identified based on the dynamic anti-counterfeiting point characteristics, and the authenticity of the target certificate is determined according to the authenticity results corresponding to the static anti-counterfeiting points and the authenticity results corresponding to the dynamic anti-counterfeiting points.
In an embodiment of the present application, after the server 103 identifies the authenticity of the target certificate 104, the identification result may be returned to the terminal 101 through the network 102, and the terminal 101 may display the identification result of the target certificate 104 to the user.
The certificate authenticity identification method provided by the embodiment of the application is generally executed by the server 103, the server 103 is configured to receive a plurality of certificate images of the target certificate 104 uploaded by the terminal 101, and identify authenticity of the target certificate 104 based on the plurality of certificate images, and accordingly, a certificate authenticity identification device is generally disposed in the server 103. However, it is easily understood by those skilled in the art that the certificate authenticity identification method provided in the embodiment of the present application may also be executed by the terminal 101, and accordingly, the certificate authenticity identification apparatus may also be disposed in the terminal 101, which is not particularly limited in the exemplary embodiment. For example, in an exemplary embodiment, the terminal 101 is configured to capture and acquire a plurality of certificate images of the target certificate 104, and identify the authenticity of the target certificate 104 based on the certificate authenticity identification method proposed in the present application.
It should be noted that: if the certificate authenticity identification method provided by the embodiment of the application is executed by the server 103, the client running on the terminal 101 can realize certificate authenticity identification through a webpage call request service mode based on the triggering of a user; if the certificate authenticity identification method provided by the embodiment of the application is executed by the terminal 101, the client running on the terminal 101 may call a certificate authenticity identification SDK (Software Development Kit) to provide a certificate authenticity identification function. Certainly, the client may also call the SDK to determine whether the acquired certificate image is standard, and the server 103 provides an authentication service to quickly identify the authenticity of the certificate.
The implementation details of the technical solution of the embodiment of the present application are set forth in detail below:
fig. 2 shows a flowchart of a certificate authenticity identification method according to an embodiment of the application, which may be performed by a device having a calculation processing function, such as the server 103 or the terminal 101 shown in fig. 1. Referring to fig. 2, the method for identifying authenticity of a certificate at least comprises steps S210 to S240, which are described in detail as follows:
in step S210, dynamic anti-counterfeit dots and static anti-counterfeit dots included in a plurality of certificate images of the target certificate are detected, and the plurality of certificate images are obtained by image capturing the target certificate from different angles.
In an embodiment of the present application, the target document may be an identity card, a passport, a social security card, a medical security card, or the like, and the dynamic anti-counterfeit point may be an identifier with an anti-counterfeit effect, such as color-changing ink, dynamic printing, a hologram, a laser image, a three-dimensional relief, or the like, in which attribute information of the document changes when the document is in different postures. The static anti-counterfeiting point is an anti-counterfeiting mark which can not change due to different angles or illumination of the certificate.
Generally speaking, a forged certificate usually does not include anti-counterfeiting points, or only includes partial anti-counterfeiting points, or the anti-counterfeiting points are different from a real certificate (for example, dynamic anti-counterfeiting points on the forged certificate do not change due to changes in angle and illumination, or the changing mode is different from that of the real certificate), so that a plurality of certificate images obtained by image acquisition of a target certificate at different angles can be acquired, and the authenticity identification result of the certificate can be comprehensively determined based on the dynamic anti-counterfeiting points and the static anti-counterfeiting points.
In one embodiment of the application, the image capture device can capture a video stream containing a target document from different angles and then obtain a plurality of document images from the video stream; or a plurality of document images of the target document can be directly acquired through different acquisition angles. Specifically, after detecting a certificate image acquisition request, the image acquisition device can start the camera to acquire images of a target certificate through different angles so as to acquire video streams or a plurality of certificate images acquired from different angles.
In one embodiment of the present application, as shown in fig. 3, when capturing an image of a target document, the target document may be flipped at different angles, and the image capturing device 301 captures an image of the target document flipped to different positions (e.g., position a, position B, position C, and position D shown in fig. 3), so as to obtain a video stream or a plurality of document images.
In one embodiment of the present application, as shown in fig. 4, the target document may be captured by different angles by placing the target document in a fixed position, changing the image capturing device 401 to different positions (e.g., position a, position b, position c, and position d shown in fig. 3), and capturing images of the target document at different capturing angles, so as to obtain a video stream or a plurality of document images.
In addition, in other embodiments of the present application, the locations of both the target document and the camera device may be varied to capture a video stream or a plurality of document images.
In an embodiment of the present application, when capturing a video stream or a plurality of certificate images of a target certificate, a position of the target certificate included in a video image frame in the captured video stream or a captured certificate image may also be detected, and if the detected position of the target certificate does not meet a set condition, the capturing may be performed again until the position of the target certificate included in the captured video image frame or certificate image meets the set condition. Optionally, if the detected target document is located outside the video image frame or document picture, or the detected target document is too small or too large in the video image frame or document picture (the too small or too large is caused by too far or too close distance between the camera and the target document when shooting), the user may be prompted to capture again.
In an embodiment of the present application, the position of the target document included in the video image frame can be detected in the following manner (since the position of the target document in the document picture is detected similarly, the following description takes the position of the target document included in the video image frame as an example:
performing downsampling processing on a video image frame through a plurality of convolution blocks which are sequentially connected, wherein a first convolution block in the plurality of convolution blocks is used for performing downsampling processing on the video image frame, an i +1 th convolution block in the plurality of convolution blocks is used for performing downsampling processing on an output feature map of the i-th convolution block, and i is larger than 0;
sequentially carrying out upsampling processing on the corresponding characteristic diagram of the (i + 1) th volume block in the plurality of volume blocks, merging the result of the upsampling processing with the output characteristic diagram of the ith volume block, and taking the merged result as the corresponding characteristic diagram of the ith volume block, wherein the upsampling processing and the downsampling processing have the same sampling scale;
and identifying the position of a target certificate contained in the video image frame according to the corresponding characteristic map of the first volume block in the plurality of volume blocks. It should be noted that the corresponding characteristic map of the last volume block in the plurality of volume blocks is the output characteristic map of the last volume block.
Specifically, as shown in fig. 5, for one video image frame 500, a feature map 501 (the feature map 501 is an output feature map of the 1 st convolution block) is obtained by performing convolution down-sampling on one convolution block by 2 × 2 (the specific scale is only an example), then a feature map 502 (the feature map 502 is an output feature map of the 2 nd convolution block) is obtained by continuing convolution down-sampling on 2 × 2, and by analogy, a feature map 503 and a feature map 504 are obtained (the feature map 503 is an output feature map of the 3 rd convolution block, the feature map 504 is an output feature map of the 4 th convolution block, and this embodiment takes 4 convolution blocks as an example for explanation). The corresponding feature map 504' of the 4 th volume block (i.e. the last volume block in the 4 sequentially connected volume blocks) is up-sampled by 2 × 2 (since the 4 th volume block is the last volume block, the corresponding feature map of the 4 th volume block is the output feature map of the 4 th volume block), and is combined with the output feature map 503 of the 3 rd volume block to obtain the corresponding feature map 503' of the 3 rd volume block, then the corresponding feature map 503' of the 3 rd volume block is up-sampled by 2 × 2, and is combined with the output feature map 502 of the 2 nd volume block to obtain the corresponding feature map 502' of the 2 nd volume block, the corresponding feature map 502' of the 2 nd volume block is up-sampled by 2 × 2, and is combined with the output feature map 501 of the 1 st volume block to obtain the corresponding feature map 501' of the 1 st volume block, and the feature map 501' is the feature image frame with the same size as the video image 500, and finally, inputting the feature map into a sigmoid function to obtain an edge segmentation result of the target certificate, wherein the position of a white frame line in 505 is the position of the detected target certificate.
In an embodiment of the application, when a video stream or a plurality of certificate images of a target certificate are collected, a turning angle of the target certificate included in a video image frame in the collected video stream or a collected certificate image can be detected, and if the detected turning angle of the target certificate does not meet a set condition, the collection can be performed again until the turning angle of the target certificate included in the collected video image frame or certificate image meets the set condition. Optionally, the user may be prompted to re-capture if the detected flip angle of the target document is too large or too small.
In an embodiment of the present application, detecting a flip angle of a target certificate included in a video image frame in a video stream (since the manner of detecting the flip angle of the target certificate in a certificate picture is similar, the following description takes detecting the flip angle of the target certificate included in the video image frame as an example), may be performing target certificate detection in the video image frame included in the video stream to identify a certificate detection frame including the target certificate in the video image frame, and then determining the flip angle of the target certificate included in the video image frame according to a side length ratio of the certificate detection frame identified in the video image frame.
For example, a proportional inverse cosine function of the left side length of the certificate detection frame and the left side length of the target certificate can be calculated to obtain a first angle, similarly, a proportional inverse cosine function of the right side length of the certificate detection frame and the right side length of the target certificate can be calculated to obtain a second angle, and the sum of the first angle and the second angle is averaged to obtain the turnover angle of the target certificate.
In an embodiment, the side length ratio of two adjacent sides of the certificate detection frame and the side length ratio of two adjacent sides of the target certificate may also be calculated, and then the turning angle of the target certificate included in each video image frame is determined according to the corresponding relationship between the side length ratio of two adjacent sides of the certificate detection frame in each video image frame and the side length ratio of two adjacent sides of the target certificate. For example, the ratio relation between the two adjacent side length ratios of the certificate detection frame and the target certificate is calculated, and the turning angle corresponding to the ratio relation is determined according to the ratio relation. In the embodiment, the method for determining the turning angle through the corresponding relation between the two adjacent side length ratios of the target certificate and the certificate detection frame has better robustness and cannot be influenced by different sizes of the target certificates in different video image frames.
In an embodiment of the present application, each video image frame may be detected by using an image detection model, where a training sample of the image detection model includes a video image frame sample labeled with a certificate detection frame, and an enhanced image obtained by performing image enhancement on the video image frame sample. Optionally, video image frames included in the video stream may be input into the image detection model, and each video image frame is detected by using the image detection model, so as to obtain a certificate detection frame including the target certificate in each video image frame.
In one embodiment of the present application, the image detection model may use PVAnet (Performance Vs Accuracy Net), which may be faster while maintaining detection Accuracy. In the training process for PVAnet, the selected training samples include: the certificate detection method comprises the steps of marking a video image frame sample with a certificate detection frame, and carrying out image enhancement processing on the video image frame sample to obtain an enhanced image. Alternatively, the enhanced image may be an image obtained by performing image enhancement processing, such as performing enhancement processing on video image frame samples by using methods such as rotation, brightness, contrast, and noise.
Continuing to refer to fig. 2, in step S220, image feature information of the position of the static anti-counterfeit point is extracted to obtain a static anti-counterfeit point feature, and image feature information of the position of the dynamic anti-counterfeit point and change feature information of the dynamic anti-counterfeit point among the plurality of certificate images are extracted to obtain a dynamic anti-counterfeit point feature.
In an embodiment of the present application, the static anti-counterfeiting point feature information is two-dimensional image feature information, so that the image feature information of the position where the static anti-counterfeiting point is located can be extracted as the static anti-counterfeiting point feature, for example, the static anti-counterfeiting point feature can be extracted by an SIFT (Scale-invariant feature transform) algorithm, or the HOG (Histogram of Oriented Gradient) feature can be extracted as the static anti-counterfeiting point feature, or the static anti-counterfeiting point feature can be extracted by a two-dimensional convolutional neural network. For the dynamic anti-counterfeiting point, not only the image characteristic information of the position of the static anti-counterfeiting point needs to be considered, but also the time sequence dimension needs to be added on the basis to capture the change characteristics of the dynamic anti-counterfeiting point among multiple frames of the video, and the characteristics of the dynamic anti-counterfeiting point can be extracted by adopting a three-dimensional convolution network, which is detailed later.
In step S230, the authenticity result corresponding to each static anti-counterfeit point is identified based on the static anti-counterfeit point characteristics, and the authenticity result corresponding to each dynamic anti-counterfeit point is identified based on the dynamic anti-counterfeit point characteristics.
In an embodiment of the present application, the authenticity result corresponding to each static anti-counterfeiting point may be determined according to the first characteristic value interval where the static anti-counterfeiting point feature of each static anti-counterfeiting point is located and the authenticity result associated with the first characteristic value interval. For example, the range of the characteristic value interval of the counterfeit-proof point can be set in advance, and then the counterfeit result of the static counterfeit-proof point can be determined according to the range of the characteristic value interval where the static counterfeit-proof point is located.
Similarly, the authenticity result corresponding to each dynamic anti-counterfeiting point can be determined according to the second characteristic value interval where the dynamic anti-counterfeiting point characteristic of each dynamic anti-counterfeiting point is located and the authenticity result associated with the second characteristic value interval.
In one embodiment of the present application, the authenticity classification method can also be used to determine the authenticity results of the static anti-counterfeiting points and the dynamic anti-counterfeiting points. For example, an SVM (Support Vector Machine) classifier is used to classify the authenticity of the anti-counterfeit point, or the authenticity of the anti-counterfeit point is classified through a full connection layer in a neural network.
In one embodiment of the present application, a specified video image frame may be extracted from a video stream containing the target document, and the specified video image frame may be all video image frames in the video stream, or may be one or more video image frames extracted from the video stream at set intervals, or may also be a video image frame with the target document in a horizontal position. And then extracting image characteristic information of the position of the static anti-counterfeiting point in the appointed video image frame. Based on this, in an embodiment of the present application, the authenticity result of the static anti-counterfeiting point included in each designated video image frame may be identified according to the static anti-counterfeiting point feature extracted from each designated video image frame, then the authenticity result of the same static anti-counterfeiting point in each designated video image frame may be determined according to the authenticity result of the static anti-counterfeiting point included in each designated video image frame, and then the authenticity result of each static anti-counterfeiting point on the target certificate may be calculated according to the authenticity result of the same static anti-counterfeiting point in each designated video image frame.
Specifically, for any video image frame, the technical solutions in the foregoing embodiments may be adopted to detect the static anti-counterfeiting point included therein and identify the authenticity result of the static anti-counterfeiting point therein. And then, the authenticity results of the same static anti-counterfeiting points contained in the extracted appointed video image frame are integrated to obtain the authenticity results of each static anti-counterfeiting point. For example, the authenticity result may be an authenticity confidence, and further, the authenticity confidences of the same static anti-counterfeiting points included in the designated video image frame may be averaged, and then the obtained average value is used as the authenticity result of each static anti-counterfeiting point.
It should be noted that, if the authenticity result of the static anti-counterfeiting point is determined by directly collecting multiple document images instead of extracting the designated video image frame from the video stream, the specific processing manner is similar to the scheme of determining the authenticity result of the static anti-counterfeiting point based on extracting the designated video image frame from the video stream, and is not repeated.
In one embodiment of the present application, at least one group of video image frames may be extracted from a video stream containing a target document, and then image feature information of a position where a dynamic anti-counterfeiting point is located and change feature information of the dynamic anti-counterfeiting point are extracted from the at least one group of video image frames. Based on this, in an embodiment of the present application, the authenticity result of the dynamic anti-counterfeiting point included in each group of video image frames may be identified according to the image feature information of the position of the dynamic anti-counterfeiting point extracted from each group of video image frames and the change feature information of the dynamic anti-counterfeiting point, then the authenticity result of the same dynamic anti-counterfeiting point in each group of video image frames may be determined according to the authenticity result of the dynamic anti-counterfeiting point included in each group of video image frames, and the authenticity result of each dynamic anti-counterfeiting point on the target certificate may be calculated according to the authenticity result of the same dynamic anti-counterfeiting point in each group of video image frames.
Specifically, for any group of video image frames, the technical solutions in the foregoing embodiments may be adopted to detect the dynamic anti-counterfeiting points included therein and identify the authenticity of the dynamic anti-counterfeiting points therein. And then, the authenticity results of the same dynamic anti-counterfeiting points contained in each extracted group of video image frames are integrated to obtain the authenticity results of each dynamic anti-counterfeiting point. For example, the authenticity result may be an authenticity confidence, and further, the authenticity confidences of the same dynamic anti-counterfeiting points included in each group of video image frames may be averaged, and then the obtained average value is used as the authenticity result of each dynamic anti-counterfeiting point.
Of course, if the at least one group of video image frames are not extracted from the video stream to determine the authenticity result of the dynamic anti-counterfeiting point, but a plurality of certificate images are directly collected to determine the authenticity result of the dynamic anti-counterfeiting point, the specific processing mode is similar to the scheme of determining the authenticity result of the dynamic anti-counterfeiting point based on the at least one group of video image frames extracted from the video stream, for example, the at least one group of certificate images can be obtained by dividing according to the plurality of certificate images, and then authenticity identification is performed, which is not repeated.
In an embodiment of the present application, as described in the foregoing embodiment, the characteristics of the dynamic anti-counterfeit points may be extracted through a three-dimensional convolution network, and meanwhile, the authenticity result corresponding to the dynamic anti-counterfeit points may also be output. Specifically, a plurality of document images (which may be extracted from a video stream containing a target document) containing the dynamic anti-counterfeiting points may be input to the three-dimensional convolution network, so as to extract a multi-dimensional feature map of the dynamic anti-counterfeiting points through the three-dimensional convolution network, and then the multi-dimensional feature map is converted into a one-dimensional feature map through a down-sampling unit in the three-dimensional convolution network, and an authenticity result corresponding to the dynamic anti-counterfeiting points is output through a full-connection layer in the three-dimensional convolution network.
Alternatively, a schematic diagram of the three-dimensional convolution network identifying the authenticity result corresponding to the dynamic anti-counterfeit point can be shown in fig. 6, and as an example, 4 convolution blocks may be adopted, where the 4 convolution blocks are serially connected in sequence, each convolution block is a structure of conv3d + BN (Batch Normalization) layer + Relu (Rectified Linear Unit), and the feature units of the 4 convolution blocks respectively correspond to the 4 columns in fig. 6. The dashed line connection between the convolution features in fig. 6 is used to indicate that one feature cell of the next layer (i.e., shown as a cube in fig. 6, which represents one cell in the feature map of the layer and represents a feature cell of the three-dimensional convolution) is convolved by adjacent feature cells of the previous layer. And finally, converting the multi-dimensional feature map into a one-dimensional feature vector 601, and outputting the authenticity confidence corresponding to the anti-counterfeiting point through the full connection layer. The authenticity confidence may be: true + confidence, and false + confidence. For example, 99.3% of true evidence; 0.7 percent of false syndrome.
Continuing to refer to fig. 2, in step S240, the authenticity of the target document is determined according to the authenticity result corresponding to each static anti-counterfeiting point and the authenticity result corresponding to each dynamic anti-counterfeiting point.
In an embodiment of the application, if the authenticity result includes the authenticity confidence, the authenticity confidence corresponding to each static anti-counterfeiting point and the authenticity confidence corresponding to each dynamic anti-counterfeiting point may be weighted according to the weight of each static anti-counterfeiting point and the weight of each dynamic anti-counterfeiting point to obtain an authenticity confidence comprehensive value, and the authenticity of the target certificate is determined according to the authenticity confidence comprehensive value.
For example, assume that the target document has 1 static anti-counterfeit dot and 2 dynamic anti-counterfeit dots, the weight of the static anti-counterfeit dot a is 0.2, the weight of the dynamic anti-counterfeit dot b is 0.4, the weight of the dynamic anti-counterfeit dot c is 0.4, and the confidence coefficient of the static anti-counterfeit dot a is: true certificate 0.4; the confidence coefficient of the dynamic anti-counterfeiting point b is as follows: 0.7 of counterfeit evidence; if the confidence of the dynamic anti-counterfeit point c is 0.5, the comprehensive confidence value of the target certificate as the true certificate can be calculated to be 0.2 × 0.4+0.4 × (1-0.7) +0.4 × 0.5 ═ 0.4.
After the comprehensive value of the confidence coefficient of authenticity of the target certificate is obtained through calculation, the comprehensive value of the confidence coefficient of authenticity can be compared with a preset threshold, if the comprehensive value of the confidence coefficient of the target certificate as a true certificate is larger than the preset threshold, the target certificate is judged as the true certificate, otherwise, if the comprehensive value of the confidence coefficient of the target certificate as the true certificate is smaller than or equal to the preset threshold, the target certificate is judged as a false certificate. The preset threshold value can be set according to actual conditions.
To sum up, the technical scheme of the embodiment of the application mainly identifies the authenticity of the certificate based on the dynamic anti-counterfeiting points and the static anti-counterfeiting points on the certificate image, for the static anti-counterfeiting points, the image characteristic information of the positions of the static anti-counterfeiting points is considered, for the dynamic anti-counterfeiting points, the image characteristic information of the positions of the dynamic anti-counterfeiting points is considered, the change characteristic information of the dynamic anti-counterfeiting points among a plurality of certificate images is considered, the authenticity results corresponding to the static anti-counterfeiting points and the authenticity results corresponding to the dynamic anti-counterfeiting points can be determined firstly, and the authenticity of the target certificate is identified according to the authenticity results corresponding to the static anti-counterfeiting points and the authenticity results corresponding to the dynamic anti-counterfeiting points, so that the accuracy of authenticity identification is improved.
As shown in fig. 7, in an embodiment of the present application, a method for identifying authenticity of a certificate may include the following steps:
in step S701, after the user takes a picture of the certificate, the position of the certificate in the image is detected.
In one embodiment of the application, a user can be guided to hold a certificate and shoot the certificate according to a specific action to obtain a shot video, and the specific action can be to enable the dynamic anti-counterfeiting point of the certificate under the action to have a relatively obvious change. For example, for hong Kong ID card 03 edition, the dynamic anti-counterfeiting points include color-changing ink, dynamically printed mark 'HK', dynamically printed portrait, etc., and the dynamic anti-counterfeiting points have obvious changes when the certificate is turned over up and down, so that a user can be guided to turn over the certificate upwards at the positive relative lens horizontal position when shooting a video, then return to the positive position, and then turn over downwards.
Step S702, judging whether the position of the certificate in the image meets the standard, if so, respectively carrying out dynamic anti-counterfeiting point identification and static anti-counterfeiting point identification, and obtaining the counterfeit identification result of the certificate based on the identification result of the dynamic anti-counterfeiting point and the identification result of the static anti-counterfeiting point. And if the position of the certificate in the image does not meet the specification, returning prompt information to enable the user to shoot again.
In one embodiment of the application, for a video image frame in a captured video, the position of a certificate is acquired to determine whether the specification is met. The method comprises the following steps of obtaining the position of the certificate, selecting an algorithm such as Hough line detection to detect four edges of the certificate, and combining to obtain the position coordinates of the certificate; a neural network method such as a method by object segmentation shown in fig. 5 or the like may also be used, or a more accurate object detection method or the like may be used. After the certificate position is acquired, whether the certificate moves out of the picture, whether the distance is too far or too close and the like can be judged to determine whether the certificate image meets the specification, and if the certificate image does not meet the specification, corresponding prompt information can be returned to guide the user to shoot again. And can also obtain the turnover angle information of the certificate, judge whether the turnover angle is too big or too small, if too big or too small, can also return the corresponding prompt message and guide the user to shoot again.
In one embodiment of the present application, since the dynamic anti-counterfeit point changes when the document is located at different angles or under different illumination, for example, the redbud flowers of the laser emblem of version 18 of hong Kong ID card can change significantly under different illumination, the dynamically printed mark "HK" in version 03 of hong Kong ID card can present different "H" or "K" characters under different angles. The static anti-counterfeiting points are anti-counterfeiting features which cannot change due to different angles or illumination, and are mostly texture characters and the like, for example, rainbow printing anti-counterfeiting points of hong Kong ID 03 edition use a micro character technology. Therefore, the dynamic anti-counterfeiting point and the static anti-counterfeiting point need to be identified respectively. Before the identification, the feature information of the static anti-counterfeiting point and the dynamic anti-counterfeiting point is extracted, and the specific extraction process and the identification process of the anti-counterfeiting point can refer to the technical scheme of the foregoing embodiment and are not described in detail.
It should be noted that, because the identification of the static anti-counterfeiting point is performed for a single frame image, the identification of the static anti-counterfeiting point can be performed for each frame of the shot video; or frames can be extracted at intervals for identification, and then the average value is taken to obtain the identification result of the static anti-counterfeiting point, so that the robustness is higher; or it can take a specific frame for discrimination, such as a horizontal frame, which can ensure a certain accuracy and at the same time has higher efficiency. For the dynamic anti-counterfeiting point, because a plurality of frames of images are required to be input to identify the change characteristics of the dynamic characteristic point, the whole video image frame of the shot video can be selected to be input, or the identification can be carried out in a segmented mode, or a plurality of groups of different video image frames can be randomly selected to be identified, and then the average value is taken as the identification result of the dynamic anti-counterfeiting point.
After the identification results of each static anti-counterfeiting point and each dynamic anti-counterfeiting point are obtained, corresponding weights can be adjusted according to the importance degree and the effect performance of each static anti-counterfeiting point and each dynamic anti-counterfeiting point to calculate and accumulate the final certificate authenticity score. If the same weight can be distributed to all anti-counterfeiting points on the certificate, the final authenticity confidence of the certificate is obtained by averaging, then a corresponding threshold value is set, and the threshold value is compared with the final authenticity confidence of the certificate to obtain the final authenticity identification result: the certificate is judged to be true certificate or false certificate.
Embodiments of the apparatus of the present application are described below, which may be used to perform the method for identifying authenticity of a document in the above-described embodiments of the present application. For details that are not disclosed in the embodiments of the apparatus of the present application, please refer to the embodiments of the method for identifying authenticity of a certificate described above in the present application.
Fig. 8 shows a block diagram of a certificate authenticity identifying arrangement according to an embodiment of the present application, which may be provided in a device having a calculation processing function, such as the server 103 or the terminal 101 shown in fig. 1.
Referring to fig. 8, a certificate authenticity identifying apparatus 800 according to an embodiment of the present application includes: the anti-counterfeiting point detection device comprises an anti-counterfeiting point detection unit 802, an extraction unit 804, a processing unit 806 and a determination unit 808.
The anti-counterfeiting point detection unit 802 is configured to detect dynamic anti-counterfeiting points and static anti-counterfeiting points included in a plurality of certificate images of a target certificate, wherein the plurality of certificate images are obtained by image acquisition of the target certificate at different angles; the extraction unit 804 is configured to extract image feature information of the position of the static anti-counterfeiting point to obtain a static anti-counterfeiting point feature, and extract image feature information of the position of the dynamic anti-counterfeiting point and change feature information of the dynamic anti-counterfeiting point among a plurality of certificate images to obtain a dynamic anti-counterfeiting point feature; the processing unit 806 is configured to identify an authenticity result corresponding to each static anti-counterfeit point based on the static anti-counterfeit point characteristics, and identify an authenticity result corresponding to each dynamic anti-counterfeit point based on the dynamic anti-counterfeit point characteristics; the determining unit 808 is configured to determine the authenticity of the target document according to the authenticity result corresponding to each static anti-counterfeiting point and the authenticity result corresponding to each dynamic anti-counterfeiting point.
In some embodiments of the present application, based on the foregoing solution, the certificate authenticity identifying apparatus 800 further includes: the device comprises an acquisition unit, a position detection unit and an acquisition unit; wherein the capture unit is configured to capture video streams containing the target document from different angles; the position detection unit is configured to detect the position of a target certificate contained in a video image frame in the video stream; the acquisition unit is further configured to: if the position detection unit detects that the position of the target certificate does not accord with the set condition, the video stream containing the target certificate is collected again until the position of the target certificate contained in the collected video image frame accords with the set condition; the acquisition unit is configured to: and if the position of the target certificate is detected to accord with the set condition, acquiring the plurality of certificate images from the video image frames contained in the video stream.
In some embodiments of the present application, based on the foregoing solution, the position detection unit is configured to: performing downsampling processing on the video image frame through a plurality of sequentially connected convolution blocks, wherein a first convolution block in the plurality of convolution blocks is used for performing downsampling processing on the video image frame, an i +1 th convolution block in the plurality of convolution blocks is used for performing downsampling processing on an output feature map of the i-th convolution block, and i is larger than 0; sequentially carrying out upsampling processing on the corresponding feature map of the (i + 1) th volume block in the plurality of volume blocks, merging the result of the upsampling processing with the output feature map of the ith volume block, and taking the merged result as the corresponding feature map of the ith volume block, wherein the upsampling processing and the downsampling processing have the same sampling scale; and identifying the position of a target certificate contained in the video image frame according to the corresponding characteristic map of the first volume block in the plurality of volume blocks.
In some embodiments of the present application, based on the foregoing solution, the certificate authenticity identifying apparatus 800 further includes: the angle detection unit is configured to detect the turning angle of a target certificate contained in a video image frame in the video stream; the acquisition unit is further configured to: if the detected turnover angle of the target certificate does not accord with the set condition, the video stream containing the target certificate is collected again until the turnover angle of the target certificate contained in the collected video image frame accords with the set condition.
In some embodiments of the present application, based on the foregoing solution, the angle detection unit is configured to: performing target certificate detection in video image frames contained in the video stream to identify a certificate detection frame containing the target certificate in the video image frames; and determining the turning angle of the target certificate contained in the video image frame according to the side length ratio of the certificate detection frame identified in the video image frame.
In some embodiments of the present application, based on the foregoing scheme, the process that the extracting unit 804 extracts the image feature information of the position where the dynamic anti-counterfeit point is located and the change feature information of the dynamic anti-counterfeit point between the multiple certificate images to obtain the dynamic anti-counterfeit point feature, and the process that the processing unit 806 identifies the authenticity result corresponding to each dynamic anti-counterfeit point based on the dynamic anti-counterfeit point feature include: inputting a plurality of certificate image frames containing the dynamic anti-counterfeiting points into a three-dimensional convolution network so as to extract a multi-dimensional feature map of the dynamic anti-counterfeiting points through the three-dimensional convolution network; and converting the multidimensional characteristic diagram into a one-dimensional characteristic diagram through a down-sampling unit in the three-dimensional convolution network, and outputting an authenticity result corresponding to the dynamic anti-counterfeiting point through a full-connection layer in the three-dimensional convolution network.
In some embodiments of the present application, based on the foregoing solution, the processing unit 806 is configured to: determining the authenticity result corresponding to each static anti-counterfeiting point according to a first characteristic value interval in which the static anti-counterfeiting point characteristic of each static anti-counterfeiting point is located and the authenticity result associated with the first characteristic value interval; and determining the authenticity result corresponding to each dynamic anti-counterfeiting point according to a second characteristic value interval where the dynamic anti-counterfeiting point of each dynamic anti-counterfeiting point is positioned and the authenticity result associated with the second characteristic value interval.
In some embodiments of the present application, based on the foregoing solution, the plurality of document images includes: a designated video image frame extracted from a video stream containing the target credential, the designated video image frame comprising any of: each video image frame in the video stream, one or more video image frames extracted from the video stream according to a set interval, and the video image frame of which the target certificate is in a horizontal position; the extraction unit 804 is configured to: and extracting image characteristic information of the position of the static anti-counterfeiting point in the appointed video image frame.
In some embodiments of the present application, based on the foregoing solution, the processing unit 806 is configured to: identifying the authenticity result of the static anti-counterfeiting points contained in each appointed video image frame based on the static anti-counterfeiting point characteristics extracted from each appointed video image frame; determining the authenticity results of the same static anti-counterfeiting point in each appointed video image frame according to the authenticity results of the static anti-counterfeiting points contained in each appointed video image frame; and calculating the authenticity result of each static anti-counterfeiting point on the target certificate according to the authenticity result of the same static anti-counterfeiting point in each appointed video image frame.
In some embodiments of the present application, based on the foregoing solution, the plurality of document images includes: at least one set of video image frames extracted from a video stream containing the target document; the extraction unit 804 is configured to: and extracting image characteristic information of the position of the dynamic anti-counterfeiting point and the change characteristic information of the dynamic anti-counterfeiting point from the at least one group of video image frames.
In some embodiments of the present application, based on the foregoing solution, the processing unit 806 is configured to: if a plurality of groups of video image frames are extracted from the video stream containing the target certificate, identifying the authenticity results of the dynamic anti-counterfeiting points contained in each group of video image frames based on the image characteristic information of the positions of the dynamic anti-counterfeiting points extracted from each group of video image frames and the change characteristic information of the dynamic anti-counterfeiting points; determining the authenticity results of the same dynamic anti-counterfeiting point in each group of video image frames according to the authenticity results of the dynamic anti-counterfeiting points contained in each group of video image frames; and calculating the authenticity result of each dynamic anti-counterfeiting point on the target certificate according to the authenticity result of the same dynamic anti-counterfeiting point in each group of video image frames.
In some embodiments of the present application, based on the foregoing scheme, the authenticity result includes an authenticity confidence; the determining unit 808 is configured to: weighting the authenticity confidence corresponding to each static anti-counterfeiting point and the authenticity confidence corresponding to each dynamic anti-counterfeiting point according to the weight of each static anti-counterfeiting point and the weight of each dynamic anti-counterfeiting point to obtain a true and false confidence comprehensive value; and determining the authenticity of the target certificate according to the authenticity confidence coefficient comprehensive value.
FIG. 9 illustrates a schematic structural diagram of a computer system suitable for use in implementing the electronic device of an embodiment of the present application.
It should be noted that the computer system 900 of the electronic device shown in fig. 9 is only an example, and should not bring any limitation to the functions and the scope of the application of the embodiments.
As shown in fig. 9, the computer system 900 includes a Central Processing Unit (CPU)901, which can perform various appropriate actions and processes, such as executing the methods described in the above embodiments, according to a program stored in a Read-Only Memory (ROM) 902 or a program loaded from a storage portion 908 into a Random Access Memory (RAM) 903. In the RAM 903, various programs and data necessary for system operation are also stored. The CPU 901, ROM 902, and RAM 903 are connected to each other via a bus 904. An Input/Output (I/O) interface 905 is also connected to bus 904.
The following components are connected to the I/O interface 905: an input portion 906 including a keyboard, a mouse, and the like; an output section 907 including a Cathode Ray Tube (CRT), a Liquid Crystal Display (LCD), and the like, a speaker, and the like; a storage portion 908 including a hard disk and the like; and a communication section 909 including a Network interface card such as a LAN (Local Area Network) card, a modem, or the like. The communication section 909 performs communication processing via a network such as the internet. The drive 910 is also connected to the I/O interface 905 as necessary. A removable medium 911 such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, or the like is mounted on the drive 910 as necessary, so that a computer program read out therefrom is mounted into the storage section 908 as necessary.
In particular, according to embodiments of the application, the processes described above with reference to the flow diagrams may be implemented as computer software programs. For example, embodiments of the present application include a computer program product comprising a computer program embodied on a computer readable medium, the computer program comprising a computer program for performing the method illustrated by the flow chart. In such an embodiment, the computer program may be downloaded and installed from a network through the communication section 909, and/or installed from the removable medium 911. The computer program executes various functions defined in the system of the present application when executed by a Central Processing Unit (CPU) 901.
It should be noted that the computer readable medium shown in the embodiments of the present application may be a computer readable signal medium or a computer readable storage medium or any combination of the two. A computer readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the foregoing. More specific examples of the computer readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a Read-Only Memory (ROM), an Erasable Programmable Read-Only Memory (EPROM), a flash Memory, an optical fiber, a portable Compact Disc Read-Only Memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the present application, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. In this application, however, a computer readable signal medium may include a propagated data signal with a computer program embodied therein, for example, in baseband or as part of a carrier wave. Such a propagated data signal may take many forms, including, but not limited to, electro-magnetic, optical, or any suitable combination thereof. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. The computer program embodied on the computer readable medium may be transmitted using any appropriate medium, including but not limited to: wireless, wired, etc., or any suitable combination of the foregoing.
The flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present application. Each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams or flowchart illustration, and combinations of blocks in the block diagrams or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.
The units described in the embodiments of the present application may be implemented by software, or may be implemented by hardware, and the described units may also be disposed in a processor. Wherein the names of the elements do not in some way constitute a limitation on the elements themselves.
As another aspect, the present application also provides a computer-readable medium, which may be contained in the electronic device described in the above embodiments; or may exist separately without being assembled into the electronic device. The computer readable medium carries one or more programs which, when executed by an electronic device, cause the electronic device to implement the method described in the above embodiments.
It should be noted that although in the above detailed description several modules or units of the device for action execution are mentioned, such a division is not mandatory. Indeed, the features and functionality of two or more modules or units described above may be embodied in one module or unit, according to embodiments of the application. Conversely, the features and functions of one module or unit described above may be further divided into embodiments by a plurality of modules or units.
Through the above description of the embodiments, those skilled in the art will readily understand that the exemplary embodiments described herein may be implemented by software, or by software in combination with necessary hardware. Therefore, the technical solution according to the embodiments of the present application can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, a usb disk, a removable hard disk, etc.) or on a network, and includes several instructions to enable a computing device (which can be a personal computer, a server, a touch terminal, or a network device, etc.) to execute the method according to the embodiments of the present application.
Other embodiments of the present application will be apparent to those skilled in the art from consideration of the specification and practice of the embodiments disclosed herein. This application is intended to cover any variations, uses, or adaptations of the invention following, in general, the principles of the application and including such departures from the present disclosure as come within known or customary practice within the art to which the invention pertains.
It will be understood that the present application is not limited to the precise arrangements described above and shown in the drawings and that various modifications and changes may be made without departing from the scope thereof. The scope of the application is limited only by the appended claims.
Claims (15)
1. A method for identifying authenticity of a certificate is characterized by comprising the following steps:
detecting dynamic anti-counterfeiting points and static anti-counterfeiting points contained in a plurality of certificate images of a target certificate, wherein the plurality of certificate images are obtained by carrying out image acquisition on the target certificate at different angles;
extracting image characteristic information of the position of the static anti-counterfeiting point to obtain the characteristic of the static anti-counterfeiting point, and extracting image characteristic information of the position of the dynamic anti-counterfeiting point and change characteristic information of the dynamic anti-counterfeiting point among a plurality of certificate images to obtain the characteristic of the dynamic anti-counterfeiting point;
identifying the authenticity result corresponding to each static anti-counterfeiting point based on the static anti-counterfeiting point characteristics, and identifying the authenticity result corresponding to each dynamic anti-counterfeiting point based on the dynamic anti-counterfeiting point characteristics;
and determining the authenticity of the target certificate according to the authenticity result corresponding to each static anti-counterfeiting point and the authenticity result corresponding to each dynamic anti-counterfeiting point.
2. The method of claim 1, further comprising:
collecting video streams containing the target certificate through different angles;
detecting the position of a target certificate contained in a video image frame in the video stream;
if the position of the target certificate is detected to be not in accordance with the set condition, the video stream containing the target certificate is collected again until the position of the target certificate contained in the collected video image frame is in accordance with the set condition;
and if the position of the target certificate is detected to accord with the set condition, acquiring the plurality of certificate images from the video image frames contained in the video stream.
3. The method for identifying the authenticity of a document according to claim 2, wherein detecting the position of a target document contained in a video image frame in the video stream comprises:
performing downsampling processing on the video image frame through a plurality of sequentially connected convolution blocks, wherein a first convolution block in the plurality of convolution blocks is used for performing downsampling processing on the video image frame, an i +1 th convolution block in the plurality of convolution blocks is used for performing downsampling processing on an output feature map of the i-th convolution block, and i is larger than 0;
sequentially carrying out upsampling processing on the corresponding feature map of the (i + 1) th volume block in the plurality of volume blocks, merging the result of the upsampling processing with the output feature map of the ith volume block, and taking the merged result as the corresponding feature map of the ith volume block, wherein the upsampling processing and the downsampling processing have the same sampling scale;
and identifying the position of a target certificate contained in the video image frame according to the corresponding characteristic map of the first volume block in the plurality of volume blocks.
4. The method of claim 2, further comprising:
detecting the turning angle of a target certificate contained in a video image frame in the video stream;
if the detected turnover angle of the target certificate does not accord with the set condition, the video stream containing the target certificate is collected again until the turnover angle of the target certificate contained in the collected video image frame accords with the set condition.
5. The method for identifying the authenticity of a certificate as claimed in claim 4, wherein detecting the flip angle of the target certificate contained in the video image frame in the video stream comprises:
performing target certificate detection in video image frames contained in the video stream to identify a certificate detection frame containing the target certificate in the video image frames;
and determining the turning angle of the target certificate contained in the video image frame according to the side length ratio of the certificate detection frame identified in the video image frame.
6. The method for identifying the authenticity of a document according to claim 1, wherein the steps of extracting image feature information of the position of the dynamic anti-counterfeiting point and change feature information of the dynamic anti-counterfeiting point among a plurality of document images to obtain the characteristics of the dynamic anti-counterfeiting point, and identifying the authenticity result corresponding to each dynamic anti-counterfeiting point based on the characteristics of the dynamic anti-counterfeiting point comprise:
inputting a plurality of certificate images containing the dynamic anti-counterfeiting points into a three-dimensional convolution network so as to extract a multi-dimensional feature map of the dynamic anti-counterfeiting points through the three-dimensional convolution network;
and converting the multidimensional characteristic diagram into a one-dimensional characteristic diagram through a down-sampling unit in the three-dimensional convolution network, and outputting an authenticity result corresponding to the dynamic anti-counterfeiting point through a full-connection layer in the three-dimensional convolution network.
7. The method of claim 1, wherein the document is authenticated,
based on the corresponding true and false result of static anti-fake point feature identification includes: determining the authenticity result corresponding to each static anti-counterfeiting point according to a first characteristic value interval in which the static anti-counterfeiting point characteristic of each static anti-counterfeiting point is located and the authenticity result associated with the first characteristic value interval;
based on the true and false result that each dynamic anti-fake point corresponds of dynamic anti-fake point feature identification includes: and determining the authenticity result corresponding to each dynamic anti-counterfeiting point according to a second characteristic value interval where the dynamic anti-counterfeiting point of each dynamic anti-counterfeiting point is positioned and the authenticity result associated with the second characteristic value interval.
8. The method of claim 1, wherein the plurality of document images include: a designated video image frame extracted from a video stream containing the target credential, the designated video image frame comprising any of: each video image frame in the video stream, one or more video image frames extracted from the video stream according to a set interval, and the video image frame of which the target certificate is in a horizontal position;
extracting the image characteristic information of the position of the static anti-counterfeiting point, comprising the following steps: and extracting image characteristic information of the position of the static anti-counterfeiting point in the appointed video image frame.
9. The method for identifying the authenticity of the document according to claim 8, wherein identifying the authenticity result corresponding to each static anti-counterfeiting point based on the characteristics of the static anti-counterfeiting points comprises:
identifying the authenticity result of the static anti-counterfeiting points contained in each appointed video image frame based on the static anti-counterfeiting point characteristics extracted from each appointed video image frame;
determining the authenticity results of the same static anti-counterfeiting point in each appointed video image frame according to the authenticity results of the static anti-counterfeiting points contained in each appointed video image frame;
and calculating the authenticity result of each static anti-counterfeiting point on the target certificate according to the authenticity result of the same static anti-counterfeiting point in each appointed video image frame.
10. The method of claim 1, wherein the plurality of document images include: at least one set of video image frames extracted from a video stream containing the target document;
extracting the image characteristic information of the position of the dynamic anti-counterfeiting point and the change characteristic information of the dynamic anti-counterfeiting point among a plurality of certificate images, wherein the extracting comprises the following steps:
and extracting image characteristic information of the position of the dynamic anti-counterfeiting point and the change characteristic information of the dynamic anti-counterfeiting point from the at least one group of video image frames.
11. The method of claim 10, wherein identifying the authenticity of each static anti-counterfeit point based on the static anti-counterfeit point characteristics if a plurality of sets of video image frames are extracted from a video stream containing the target document comprises:
identifying the authenticity results of the dynamic anti-counterfeiting points contained in each group of video image frames based on the image characteristic information of the positions of the dynamic anti-counterfeiting points extracted from each group of video image frames and the change characteristic information of the dynamic anti-counterfeiting points;
determining the authenticity results of the same dynamic anti-counterfeiting point in each group of video image frames according to the authenticity results of the dynamic anti-counterfeiting points contained in each group of video image frames;
and calculating the authenticity result of each dynamic anti-counterfeiting point on the target certificate according to the authenticity result of the same dynamic anti-counterfeiting point in each group of video image frames.
12. The method of any one of claims 1 to 11, wherein the authenticity result includes an authenticity confidence;
determining the authenticity of the target certificate according to the authenticity results corresponding to the static anti-counterfeiting points and the authenticity results corresponding to the dynamic anti-counterfeiting points, wherein the authenticity determination method comprises the following steps:
weighting the authenticity confidence corresponding to each static anti-counterfeiting point and the authenticity confidence corresponding to each dynamic anti-counterfeiting point according to the weight of each static anti-counterfeiting point and the weight of each dynamic anti-counterfeiting point to obtain a true and false confidence comprehensive value;
and determining the authenticity of the target certificate according to the authenticity confidence coefficient comprehensive value.
13. An apparatus for authenticating a document, comprising:
the detection unit is configured to detect dynamic anti-counterfeiting points and static anti-counterfeiting points contained in a plurality of certificate images of a target certificate, wherein the plurality of certificate images are obtained by carrying out image acquisition on the target certificate through different angles;
the extraction unit is configured to extract image characteristic information of the position of the static anti-counterfeiting point to obtain a static anti-counterfeiting point characteristic, and extract image characteristic information of the position of the dynamic anti-counterfeiting point and change characteristic information of the dynamic anti-counterfeiting point among a plurality of certificate images to obtain a dynamic anti-counterfeiting point characteristic;
the processing unit is configured to identify the authenticity result corresponding to each static anti-counterfeiting point based on the static anti-counterfeiting point characteristics and identify the authenticity result corresponding to each dynamic anti-counterfeiting point based on the dynamic anti-counterfeiting point characteristics;
and the determining unit is configured to determine the authenticity of the target certificate according to the authenticity results corresponding to the static anti-counterfeiting points and the authenticity results corresponding to the dynamic anti-counterfeiting points.
14. A computer-readable medium, on which a computer program is stored, which, when being executed by a processor, carries out a method of authenticating a document as claimed in any one of claims 1 to 12.
15. An electronic device, comprising:
one or more processors;
storage means for storing one or more programs which, when executed by the one or more processors, cause the one or more processors to carry out a method of document authenticity identification as claimed in any one of claims 1 to 12.
Priority Applications (4)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011179992.0A CN112200136A (en) | 2020-10-29 | 2020-10-29 | Certificate authenticity identification method and device, computer readable medium and electronic equipment |
| PCT/CN2021/121138 WO2022089124A1 (en) | 2020-10-29 | 2021-09-28 | Certificate authenticity identification method and apparatus, computer-readable medium, and electronic device |
| EP21884854.7A EP4109332A4 (en) | 2020-10-29 | 2021-09-28 | Certificate authenticity identification method and apparatus, computer-readable medium, and electronic device |
| US17/965,549 US20230030792A1 (en) | 2020-10-29 | 2022-10-13 | Document authenticity identification method and apparatus, computer-readable medium, and electronic device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011179992.0A CN112200136A (en) | 2020-10-29 | 2020-10-29 | Certificate authenticity identification method and device, computer readable medium and electronic equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112200136A true CN112200136A (en) | 2021-01-08 |
Family
ID=74011937
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011179992.0A Pending CN112200136A (en) | 2020-10-29 | 2020-10-29 | Certificate authenticity identification method and device, computer readable medium and electronic equipment |
Country Status (4)
| Country | Link |
|---|---|
| US (1) | US20230030792A1 (en) |
| EP (1) | EP4109332A4 (en) |
| CN (1) | CN112200136A (en) |
| WO (1) | WO2022089124A1 (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113034433A (en) * | 2021-01-14 | 2021-06-25 | 腾讯科技（深圳）有限公司 | Data authentication method, device, equipment and medium |
| CN113240043A (en) * | 2021-06-01 | 2021-08-10 | 平安科技（深圳）有限公司 | False identification method, device and equipment based on multi-picture difference and storage medium |
| WO2021159750A1 (en) * | 2020-09-04 | 2021-08-19 | 平安科技（深圳）有限公司 | Method and apparatus for authenticating certificate, and computer device and storage medium |
| CN113378878A (en) * | 2021-04-30 | 2021-09-10 | 长城信息股份有限公司 | Identity card counterfeit identification method and electronic equipment |
| WO2022089124A1 (en) * | 2020-10-29 | 2022-05-05 | 腾讯科技（深圳）有限公司 | Certificate authenticity identification method and apparatus, computer-readable medium, and electronic device |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US11663824B1 (en) * | 2022-07-26 | 2023-05-30 | Seismic Software, Inc. | Document portion identification in a recorded video |
| CN116758296B (en) * | 2023-08-21 | 2023-12-05 | 深圳前海量子云码科技有限公司 | Method, device, equipment and medium for extracting anti-counterfeiting characteristic value of microcosmic coding code pattern |
Family Cites Families (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108229499A (en) * | 2017-10-30 | 2018-06-29 | 北京市商汤科技开发有限公司 | Certificate recognition methods and device, electronic equipment and storage medium |
| CN109446900A (en) * | 2018-09-21 | 2019-03-08 | 平安科技（深圳）有限公司 | Certificate authenticity verification method, apparatus, computer equipment and storage medium |
| CN112507889A (en) * | 2019-04-29 | 2021-03-16 | 众安信息技术服务有限公司 | Method and system for verifying certificate and certificate holder |
| CN110427972B (en) * | 2019-07-09 | 2022-02-22 | 众安信息技术服务有限公司 | Certificate video feature extraction method and device, computer equipment and storage medium |
| CN110516739B (en) * | 2019-08-27 | 2022-12-27 | 创新先进技术有限公司 | Certificate identification method, device and equipment |
| CN117237974A (en) * | 2020-01-19 | 2023-12-15 | 支付宝实验室(新加坡)有限公司 | Certificate verification method and device and electronic equipment |
| CN112200136A (en) * | 2020-10-29 | 2021-01-08 | 腾讯科技（深圳）有限公司 | Certificate authenticity identification method and device, computer readable medium and electronic equipment |
-
2020
- 2020-10-29 CN CN202011179992.0A patent/CN112200136A/en active Pending
-
2021
- 2021-09-28 EP EP21884854.7A patent/EP4109332A4/en active Pending
- 2021-09-28 WO PCT/CN2021/121138 patent/WO2022089124A1/en unknown
-
2022
- 2022-10-13 US US17/965,549 patent/US20230030792A1/en active Pending
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2021159750A1 (en) * | 2020-09-04 | 2021-08-19 | 平安科技（深圳）有限公司 | Method and apparatus for authenticating certificate, and computer device and storage medium |
| WO2022089124A1 (en) * | 2020-10-29 | 2022-05-05 | 腾讯科技（深圳）有限公司 | Certificate authenticity identification method and apparatus, computer-readable medium, and electronic device |
| CN113034433A (en) * | 2021-01-14 | 2021-06-25 | 腾讯科技（深圳）有限公司 | Data authentication method, device, equipment and medium |
| CN113034433B (en) * | 2021-01-14 | 2024-01-02 | 腾讯科技（深圳）有限公司 | Data authentication method, device, equipment and medium |
| CN113378878A (en) * | 2021-04-30 | 2021-09-10 | 长城信息股份有限公司 | Identity card counterfeit identification method and electronic equipment |
| CN113378878B (en) * | 2021-04-30 | 2022-08-16 | 长城信息股份有限公司 | Identity card counterfeit identification method and electronic equipment |
| CN113240043A (en) * | 2021-06-01 | 2021-08-10 | 平安科技（深圳）有限公司 | False identification method, device and equipment based on multi-picture difference and storage medium |
| WO2022252641A1 (en) * | 2021-06-01 | 2022-12-08 | 平安科技（深圳）有限公司 | Multi-picture difference-based forgery identification method and apparatus, device and storage medium |
| CN113240043B (en) * | 2021-06-01 | 2024-04-09 | 平安科技（深圳）有限公司 | Pseudo-identification method, device, equipment and storage medium based on multi-picture difference |
Also Published As
| Publication number | Publication date |
|---|---|
| WO2022089124A1 (en) | 2022-05-05 |
| US20230030792A1 (en) | 2023-02-02 |
| EP4109332A4 (en) | 2023-06-21 |
| EP4109332A1 (en) | 2022-12-28 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| WO2022089124A1 (en) | Certificate authenticity identification method and apparatus, computer-readable medium, and electronic device | |
| US10635946B2 (en) | Eyeglass positioning method, apparatus and storage medium | |
| US10664581B2 (en) | Biometric-based authentication method, apparatus and system | |
| KR102406432B1 (en) | Identity authentication methods and devices, electronic devices and storage media | |
| WO2018086543A1 (en) | Living body identification method, identity authentication method, terminal, server and storage medium | |
| WO2019033572A1 (en) | Method for detecting whether face is blocked, device and storage medium | |
| US11023708B2 (en) | Within document face verification | |
| WO2016150240A1 (en) | Identity authentication method and apparatus | |
| Fourati et al. | Anti-spoofing in face recognition-based biometric authentication using image quality assessment | |
| US11367310B2 (en) | Method and apparatus for identity verification, electronic device, computer program, and storage medium | |
| US20190180094A1 (en) | Document image marking generation for a training set | |
| US10936866B2 (en) | Method for detecting document fraud | |
| CN111242124B (en) | Certificate classification method, device and equipment | |
| CN111626163B (en) | Human face living body detection method and device and computer equipment | |
| CN111898520A (en) | Certificate authenticity identification method and device, computer readable medium and electronic equipment | |
| CN113111880B (en) | Certificate image correction method, device, electronic equipment and storage medium | |
| US11816946B2 (en) | Image based novelty detection of material samples | |
| JP6910236B2 (en) | Personal information registration system and personal information registration method | |
| CN110751071A (en) | Face recognition method and device, storage medium and computing equipment | |
| CN111259894B (en) | Certificate information identification method and device and computer equipment | |
| CN111950415A (en) | Image detection method and device | |
| CN113610090B (en) | Seal image identification and classification method, device, computer equipment and storage medium | |
| CN114820476A (en) | Identification card identification method based on compliance detection | |
| CN110415424B (en) | Anti-counterfeiting identification method and device, computer equipment and storage medium | |
| CN113240043A (en) | False identification method, device and equipment based on multi-picture difference and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| REG | Reference to a national code |
Ref country code: HK Ref legal event code: DE Ref document number: 40037365 Country of ref document: HK |
|
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |